Abstract
The binary segmentation of whiteboard strokes is hindered by extreme class imbalance, caused by stroke pixels that constitute only $1.79%$ of the image on average, and in addition, the thin-stroke subset averages $1.14% \pm 0.41%$ in the foreground. Standard region metrics (F1, IoU) can mask thin-stroke failures because the vast majority of the background dominates the score. In contrast, adding boundary-aware metrics and a thin-subset equity analysis changes how loss functions rank and exposes hidden trade-offs. We contribute an evaluation protocol that jointly examines region metrics, boundary metrics (BF1, B-IoU), a core/thin-subset equity analysis, and per-image robustness statistics (median, IQR, worst-case) under seeded, multi-run training with non-parametric significance testing. Five losses -- cross-entropy, focal, Dice, Dice+focal, and Tversky -- are trained three times each on a DeepLabV3-MobileNetV3 model and evaluated on 12 held-out images split into core and thin subsets. Overlap-based losses improve F1 by more than 20 points over cross-entropy ($0.663$ vs $0.438$, $p < 0.001$). In addition, the boundary metrics confirm that the gain extends to the precision of the contour. Adaptive thresholding and Sauvola binarization at native resolution achieve a higher mean F1 ($0.787$ for Sauvola) but with substantially worse worst-case performance (F1 $= 0.452$ vs $0.565$ for Tversky), exposing a consistency-accuracy trade-off: classical baselines lead on mean F1 while the learned model delivers higher worst-case reliability. Doubling training resolution further increases F1 by 12.7 points.
Abstract (translated)
白板笔迹的二值分割受到极端类别不平衡的影响，这是因为笔迹像素平均只占图像的$1.79\%$，而细线子集在前景中的占比仅为$1.14\% \pm 0.41\%$。标准区域指标（F1, IoU）可能会掩盖细线分割错误，因为绝大多数背景占据了评分的主要部分。相比之下，增加边界感知度的评估指标和对细线子集公平性的分析改变了损失函数的排序方式，并揭示了隐藏的权衡。我们提出了一种评估协议，在种子多轮训练中同时考察区域指标、边界指标（BF1, B-IoU）、核心/细线子集公平性分析以及每张图片的鲁棒统计量（中位数，IQR，最坏情况），并通过非参数显著性测试进行验证。五种损失函数——交叉熵、焦点、Dice、Dice+焦点和Tversky，在DeepLabV3-MobileNetV3模型上各自训练三次，并在12张保留的图像（分成核心集和细线子集）上进行了评估。基于重叠的损失函数使F1得分相对于交叉熵提高了超过20个百分点（$0.663$ 对比 $0.438$，$p < 0.001$）。此外，边界指标证实这种增益扩展到了轮廓精度。自适应阈值和Sauvola二值化在原生分辨率下实现了更高的平均F1得分（Sauvola的平均F1得分为$0.787$），但最坏情况下的性能表现明显较差（F1得分从$0.452$ 降到 $0.565$，对应于Tversky模型）。这揭示了一个一致性与准确性之间的权衡：经典基线在平均F1得分上处于领先地位，而学习型模型则提供了更高的最坏情况下的可靠性。将训练分辨率加倍进一步提高了F1得分为$12.7$个百分点。
URL
https://arxiv.org/abs/2603.00163
